Papers by Zhuang Ma

17 papers
SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation (2022.coling-1)

Copied to clipboard

Challenge: Existing evaluation metrics are expensive and easy to conduct but ineffective to reflect dialogue quality.
Approach: They propose a self-supervised fine-grained dialogue evaluation framework which can automatically assign fine-granular scores for arbitrarily dialogue data.
Outcome: The proposed framework is highly consistent with human evaluations and better than the state-of-the-art models.
Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models (2025.acl-long)

Copied to clipboard

Challenge: composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach: They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome: The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder (2024.findings-naacl)

Copied to clipboard

Challenge: generative diversity is a critical yet underexplored issue in natural language generation . previous approaches to enhance diversity of Transformer models have been limited by their latent variables .
Approach: They propose a framework that bridges Transformer with VAE to enhance generative diversity.
Outcome: The proposed framework improves generative diversity while maintaining generative quality.
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, vision-language models excel in many downstream tasks but struggle with spatial reasoning, which is crucial for navigation and interaction with physical environments.
Approach: They propose a framework that generates synthetic data to provide targeted supervision for VLMs across these basic spatial capabilities.
Outcome: The proposed framework disentangles 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization.
VISA: Retrieval Augmented Generation with Visual Source Attribution (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation primarily link generated content to document-level references, making it difficult for users to locate evidence among multiple content-rich retrieved documents.
Approach: They propose a novel approach that combines answer generation with visual source attribution by leveraging large vision-language models to identify evidence and highlight exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.
Outcome: The proposed approach identifies evidence and highlights exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) excel in zero-shot document ranking tasks.
Approach: They propose a prompt-based re-ranking method that requires no further training but is only feasible for reranking a handful of candidates due to computational costs.
Outcome: The proposed method can retrieve documents from the entire corpus without training and with a large amount of paired text data.
Astra: Efficient Transformer Architecture and Contrastive Dynamics Learning for Embodied Instruction Following (2025.emnlp-main)

Copied to clipboard

Challenge: Existing vision-language-action models rely on causal attention for processing sequences composed of interleaved segments from different modalities.
Approach: They propose a Transformer architecture featuring trajectory attention and learnable action queries that efficiently process segmented multimodal trajectories and predict actions for imitation learning.
Outcome: The proposed architecture performs better on three large-scale robot manipulation benchmarks than previous models.
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)

Copied to clipboard

Challenge: Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns.
Approach: They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
Outcome: The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation.
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B.
Approach: They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation.
Outcome: The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model.
Audio-centric Video Understanding Benchmark without Text Shortcut (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal large language models (MLLMs) focus on visual abilities, but audio is essential for video understanding.
Approach: They propose an audio-centric video understanding benchmark to evaluate video comprehension capabilities of multimodal LLMs with a particular focus on auditory information.
Outcome: The proposed video understanding benchmarks evaluate video comprehension capabilities of multimodal models with a particular focus on auditory information.
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach: They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome: The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.
Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency (D18-1)

Copied to clipboard

Challenge: Conditional models are frequently encountered in practice, but there has not been a rigorous theoretical analysis of NCE in this setting.
Approach: They propose to use a ranking-based and ranking-only method for conditional models to estimate parameter estimates.
Outcome: The proposed method avoids calculation of partition function or derivatives at each training step . it is closely related to negative sampling methods, now widely used in NLP .
Few-shot In-context Learning on Knowledge Base Question Answering (2023.acl-long)

Copied to clipboard

Challenge: KB-BINDER enables few-shot in-context learning over knowledge base questions . KBQA is a difficult problem due to the heterogeneity of knowledge bases .
Approach: They propose a framework that enables few-shot in-context learning over KBQA tasks.
Outcome: The proposed framework can outperform state-of-the-art models on GraphQA and MetaQA datasets.
ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing urban itinerary planning studies focus on traditional tourism, but they lack the precision and accuracy needed to create a personalized itinerary.
Approach: They propose an open-domain urban itinerary planning system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs.
Outcome: The proposed system can generate personalized urban itineraries based on user needs and scale with existing methods.
Learning From the Source Document: Unsupervised Abstractive Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for abstractive summarization are under supervised training, but obtaining high-quality and large-scale datasets for supervised learning is laboriously difficult.
Approach: They propose an unsupervised method that leverages contrastive learning to generate summaries by rewriting and paraphrasing the source documents to generate good summary.
Outcome: The proposed method outperforms baseline methods on extensive experiments on source documents and fake documents.
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference (2022.findings-acl)

Copied to clipboard

Challenge: State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking.
Approach: They propose to fine tune a pretrained encoder-decoder model using document to query generation.
Outcome: The proposed model achieves comparable results to more expensive approaches while being 6.8X faster.
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model (2024.emnlp-main)

Copied to clipboard

Challenge: Using large language models, large multimodal models struggle with basic tasks like reading time from a clock and planning a route using a road map.
Approach: They propose a multimodal self-instruct that synthesizes massive abstract images and visual reasoning instructions.
Outcome: The proposed model synthesizes 11,193 abstract images and reasoning instructions across eight visual scenarios.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations